CN103329490B - Improve method and the communication network of data transmission quality based on packet communication network - Google Patents
Improve method and the communication network of data transmission quality based on packet communication network Download PDFInfo
- Publication number
- CN103329490B CN103329490B CN201280006638.5A CN201280006638A CN103329490B CN 103329490 B CN103329490 B CN 103329490B CN 201280006638 A CN201280006638 A CN 201280006638A CN 103329490 B CN103329490 B CN 103329490B
- Authority
- CN
- China
- Prior art keywords
- port
- overload
- communication path
- network
- network node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
- H04L41/0663—Performing the actions predefined by failover planning, e.g. switching to standby network elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0852—Delays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/22—Alternate routing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/28—Routing or path finding of packets in data switching networks using route fault recovery
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/11—Identifying congestion
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
- H04L47/122—Avoiding congestion; Recovering from congestion by diverting traffic away from congested entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/18—End to end
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/29—Flow control; Congestion control using a combination of thresholds
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/30—Flow control; Congestion control in combination with information about buffer occupancy at either end or at transit nodes
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention describes the method for the quality of a kind of data transmission for improving in packet-based communication network, and this communication network includes multiple network node (K).Each described network node (K) has a number of port (P), and to these port assignment, at least one waits queue (Q) and the communication connection (KV) can set up to other network node (K) via these ports respectively.In the method for the invention, in network node (K) along the respective communication paths arrangement formed in the communications network port (P) the most described waiting queue (Q) in view of its waiting queue length be monitored.In addition from this waiting queue length, determine that the overload for involved one or more ports (P) is measured, wherein from the one or more communication path (PF1 for the port (P) through involved overload, PF2, PF3) overload tolerance in can be inferred that these data transmission in operation time delay (delay) and/or delay variation (shake).The communication path (PF1, PF2, PF3) guided via the port (P) of overload finally at least one, overload tolerance exceedes previously given threshold value.The communication path (PF2') of replacement is set up in the case of walking around the port (P) of this overload.
Description
Technical field
The present invention relates to the method for improving the quality in packet-based communication network, this communication network includes multiple network node, the most each described network node has a number of port, at least one the waiting queue of these port assignment and can set up the communication connection to other network node by these ports respectively.The invention still further relates to the network node of packet-based communication network and there is the packet-based communication network of multiple network node.
Background technology
In many distributions application on a communication network, data transmission does not allow more than, at end-to-end delay (postponing (Delay)) and/or delay variation (shake (Jitter)) aspect, the ultimate value determined, is achieved in the desired service quality of this application.This is especially applicable to such as factory automation in the case of the communication network of structure in industrial scale, crosses process automation or energy automatization.Be based only upon TDM(Time Division Multiplexing, time division multiplexing at present) network technology can meet previously given requirement to delay and jitter value along the communication path of structure in this communication network.The most suitably network technology is SDH(Synchronous Digital
Hierarchy, Synchronous Digital Hierarchy) or ATM(Asynchronous Transfer Mode, asynchronous transfer mode) network.Due to their complexity and high cost, especially in the case of calibration (Skalierung), these network technologies all can not meaningfully be used in many application scenario.
Therefore, even due to complexity and cheap cost reason in the case of calibration, it is desirable for using packet-based communication network.Such communication network e.g. Ethernet or based on IP(Internet Protocol, Internet protocol) communication network.But packet-based communication network problematically, principle determine ground it cannot be guaranteed that postpone and/or shake in terms of guarantee.
Although the bothersome extension of known Ethernet in EPA field (such as the real-time Transmission (IRT) when waiting of PROFINET), these extend through TDM and imitate communication network qualitative behavior really.But this technology by using special hardware and can only be used with high configuration consuming.
Summary of the invention
Therefore the task of the present invention is that a kind of method is described, the quality that the data utilizing the method can improve in packet-based communication network are transmitted.The network node of packet-based communication network also should be described, this network node allows to improve the quality of the data transmission in this packet-based communication network.The task of the last present invention is also described the packet-based communication network with high data transmission quality.
These tasks are by solving according to method as described below, network node and packet-based communication network.According to the present invention for the method improving the quality of the data transmission in packet-based communication network, this communication network includes multiple network node, the most each described network node has a number of port, to at least one the waiting queue of these port assignment and the communication connection to other network node can be set up via these ports respectively, wherein, by upper network management entity at least within network nodes along the respective communication paths arrangement formed in the communications network port waiting queue waiting queue length monitor；From described waiting queue length, determine that the overload for involved one or more ports is measured, from the overload tolerance of the one or more communication paths for the port through involved overload, wherein infer the operation time delay in the transmission of these data and/or delay variation；nullWhen this overload tolerance exceedes previously given threshold value，It is that at least one sets up the communication path of replacement via the port guided communication path of overload under the port walking around this overload by the upper network management entity of described network node，With avoid on the port of described overload manifest congested，Wherein said communication path is set up by described upper network management entity，The overload tolerance of the port arranged within network nodes is wherein at least considered along this new communication path when setting up new communication path，Wherein define the low first threshold of the overload tolerance of the port arranged within network nodes along new communication path，The communication path that this is new is set up in the case of exceeding this first threshold，Make not consider with lower node for this new communication path: described node has the port of at least one overload，The overload tolerance of the port of this overload exceedes this first threshold，Or do not consider that its overload tolerance of node exceedes the port of the overload of this first threshold，And wherein define the higher Second Threshold of the overload tolerance of the port arranged within network nodes along this new communication path，In the case of exceeding this Second Threshold, determine and set up the communication path of replacement for existing communication path.Correspondingly, packet-based communication network according to the present invention, this communication network includes: 1) multiple network nodes, wherein this network node includes a number of port, to at least one the waiting queue of these port assignment and the communication connection to other network node can be set up via these ports respectively, this network node includes: first device, in this network node along the respective communication paths arrangement formed in the communications network port waiting queue waiting queue length monitor；Second device, for determining overload tolerance from the waiting queue length for one or more involved ports；And inquiring about or periodically providing the device of the waiting queue length of described port for the transmission of superior network management entity for upper network management entity；And 2) for setting up the network management entity of the communication path of communication path and/or replacement in the communications network, wherein this network management entity includes: the 3rd device, by the 3rd device from that obtained by corresponding network node, for one or more ports through involved overload communication path overload tolerance infer data transmit in operation time delay and/or delay variation；null4th device，When described overload tolerance exceedes previously given threshold value，The communication path of replacement can be set up under the port walking around this overload via the port guided communication path of overload at least one by the 4th device，With avoid on the port of described overload manifest congested，This network management entity wherein said be further configured so that: at least consider the overload tolerance of the port arranged within network nodes along this new communication path when setting up new communication path，The low first threshold of the overload tolerance of the port that definition is arranged along new communication path within network nodes，The communication path that this is new is set up in the case of exceeding this first threshold，Make not consider with lower node for this new communication path: described node has the port of at least one overload，The overload tolerance of the port of this overload exceedes this first threshold，Or do not consider that its overload tolerance of node exceedes the port of the overload of this first threshold，And the higher Second Threshold that definition is measured along the overload of the port of this new communication path layout within network nodes，In the case of exceeding this Second Threshold, determine and set up the communication path of replacement for existing communication path.
The method that present invention achieves the quality transmitted for the data improving in packet-based communication network, this communication network detects multiple network nodes, the most each described network node is respectively provided with a number of port, at least one the waiting queue of these port assignment and can set up the communication connection to other network node by these ports respectively.In the method, within network nodes along the respective communication paths arrangement formed in the communications network port the most described waiting queue in view of its waiting queue length be monitored.From this waiting queue length, determine that the overload for involved one or more ports is measured, from the overload tolerance of the communication path for one or more ports through involved overload, wherein can be inferred that the operation time delay (delay) in the transmission of these data and/or delay variation (shake).When this overload tolerance exceedes previously given threshold value, at least one is set up under the port walking around this overload to the communication path of replacement via the port guided communication path of overload.
The present invention also realizes the network node of packet-based communication network, this communication network has multiple network node, wherein this network node includes a number of port, at least one the waiting queue of these port assignment and can set up the communication connection to other network node by these ports respectively.This network node includes first device, for monitoring the waiting queue of the port arranged in this network node along communication path corresponding, that formed along this communication network in view of its waiting queue length.This network node also includes the second device, for determining overload tolerance from the waiting queue length for one or more involved ports.
The present invention also realizes packet-based communication network, and this communication network includes multiple network node constructed according to the invention and for setting up the network management entity of the communication path of communication path and/or replacement in the case of using routing mechanism in the communications network.This network management entity includes the 3rd device, by the 3rd device from that obtained by corresponding network node, for one or more ports through involved overload communication path overload tolerance can be inferred that data transmit in operation time delay (delay) and/or delay variation (shake).This network management entity also includes the 4th device, when described overload tolerance exceedes previously given threshold value, can be set up the communication path of replacement under the port walking around overload via the port guided communication path of overload at least one by the 4th device.
Utilize the present invention to can be implemented in packet-based communication network really to come to a conclusion, the communication network of described communication network e.g. internet protocol-based or Ethernet.Thus obtain for the high-transmission quality in terms of the delay of the communication path thought formed in this communication network and/or shake.One advantage of action modes of the present invention is, need not intricately calculate absolute delay and/or jitter value to can determine that to there is delay in communication network and/or shake critical condition.This is especially it is assumed hereinafter that lower be suitable for: (the most there is not overload or congested conditions) in the quickest, idle communication network and postpones and/or shake to require to be complied with without any problems.Another advantage is, in order to implement action according to the present invention in this network node with little need for amendment.Another advantage is, the method also ensures the Granular Scalability in big communication network.Therefore this Granular Scalability is guaranteed, because utilizing the method for the present invention have only to for each waiting queue and network node rather than monitor delay or jitter value for each communication path.
In a kind of suitable configuration, under walking around the node including at least one port transshipped, set up the communication path of replacement.Thus the route of the communication path of this replacement gets around the node guiding of the port with overload.This is probably favourable when the performance of whole network node is adversely affected by the overload of port.
According to another configuration, in order to determine that one of following waiting queue length is processed by overload tolerance: averagely waiting queue length, wherein this averagely waiting queue length is that multiple the temporal of waiting queue length detected on the previously given time period by waiting queue averagely calculate；And/or the waiting queue length of maximum and/or by the time upper in the past and current waiting queue length determines effectively waits queue length.Based on illustrated waiting queue length, can be to postpone or shake critical communication path to determine suitable communication path.
According to the configuration that another is suitable, the communication path of described communication path and/or described replacement is set up by upper network management entity in the case of using routing mechanism.This network management entity is for setting up communication path on one's own initiative in packet-based communication network.Set up communication path by network management entity on one's own initiative and such as can be similar to MPLS(Multi Protocol Label
Switching, multi protocol label exchange) carry out.Here, the waiting queue length of some ports of the standard network node used according to the invention as good or severe communication path.Network management entity can be constructed by the control unit of one of central computer, network node or multiple computer and control unit.
In this another configuration, being inquired about the waiting queue length of the port of multiple network nodes by upper network management entity with previously given interval, wherein this network management entity is that each port determines overload tolerance.Alternatively, being transmitted the waiting queue length of the port of multiple network nodes by network node superior network management entity with time the most previously given upper interval and/or according to exceed the previously given overall situation or the single threshold value of network node, wherein this network management entity is that each port determines overload tolerance.
The most desirably, the overload tolerance of the port arranged within network nodes is at least considered along this new communication path when setting up new communication path.Thus when setting up new communication metrics, it is the most always the result when setting up this new communication path that the shortest between source node with destination node is connected.More precisely, in addition further contemplate corresponding network node or be positioned at the port in potential communication path at full capacity.
The most desirably, define the low first threshold of the overload tolerance (or waiting queue) for the port arranged within network nodes along new communication path, the communication path that this is new is so set up in the case of exceeding this first threshold, make not consider with lower node for this new communication path: these nodes have the port of at least one overload, the overload tolerance of the port of this overload exceedes this first threshold, or does not consider the port of the following overload of node: the overload tolerance of the port of these overloads exceedes this first threshold.
In another configuration, define the higher Second Threshold of the overload tolerance (or waiting waiting queue length of queue) for the port arranged along this new communication path within network nodes, determine in the case of exceeding this Second Threshold and set up the communication path for existing communication path replacement.
From there through first threshold and the setting of Second Threshold higher compared with this first threshold, the load of the port of node or overload can be controlled targetedly in terms of the data of the port transmission by network node or overload.Wait queue length determined by according to, guide new communication path while the port of overload or involved network node may be got around the most targetedly, and the communication path having passed through the port of overload changes its course.
According to the configuration that another is suitable, monitor overload tolerance (or waiting queue length) according to the class of service of involved waiting queue.If the data service of low priority also occurs in addition to the data service of high priority, the delay of the data service of low priority and/or shake may be caused to improve when the data service of high priority.Such as, this may be implemented by the disadvantageous scheduler in network node or cause by there being the packet of high priority to arrive during still sending the packet of long low priority.The critical condition that such data service by low priority causes can be identified reliably by the waiting queue length considering different business classification.By the above-mentioned strategy making the communication path determined change its course, can improve in a communication network the most at full capacity, the quality transmitted for improving data during thus result can be implemented in packet-based communication network is come to a conclusion really.
Another configuration specifies, from determining the operation time delay on involved communication path and/or postpone the end-to-end value of variation along overload tolerance determined by the waiting queue of the respective communication paths arrangement formed in the communications network or waiting queue length within network nodes.
It is dynamically used for the waiting queue length of the port of network node in combination identifying delay and/or shake critical condition to the periodically inquiry of waiting queue length or corresponding message with by node based in the case of being exceeded in previously given threshold value thus according to taking action of the present invention.The information of waiting queue length based on the port about the network node existed in the communications network, for postponing or shake critical Business Stream to calculate suitable communication path.The advantage of this action mode is, the given and scheduler enforcement of detailedization or the independence with the scheduler concept used.
Accompanying drawing explanation
The present invention is explained in more detail below by the embodiment in accompanying drawing.Wherein:
Fig. 1 illustrates the communication network of the present invention with multiple network node and upper network management entity,
Fig. 2 illustrates the communication network in Fig. 1, the most exemplarily illustrates 3 paths set up by this network management entity,
Fig. 3 illustrates the communication network in Fig. 2, and the port of overload is notified to network management entity by one of network node in the communications network,
Fig. 4 illustrates the communication network according to Fig. 2, and one of original communication path is arranged to replace route in the communications network, and
Fig. 5 illustrates the communication network in Fig. 2, set up new communication path in the communications network.
Detailed description of the invention
Fig. 1 illustrates the communication network of the present invention with multiple network node K and network management entity NM.Network node K is numbered 1 to 8, wherein the appropriate address of these digitized representations network node K.Each described network node K has a number of port P, can set up the communication connection KV to other network node K via these ports.In the present embodiment, corresponding with the quantity of port from the quantity of the communication connection of node K, wherein respective nodes can have the ratio greater amount of port of communication connection in principle.Only for the node K represented with address 1 and 5, it is equipped with its reference to port P.Communication connection KV can be based on circuit or wireless character according to the type of communication network.The most in the case of the latter it is possible that also construct the communication connection different from communication connection shown in FIG between node K.
Level is network management entity NM carried on nodek.The network management entity such as formed by central computer can exchange data with network node K via corresponding communication connection KVN.The communication connection KVN that figure 1 illustrates is only logic property, and need not be directly present between corresponding network node K and network management entity NM.What mode to be secondary for the present invention at the swapping data (wirelessly or non-wirelessly) of network management entity Yu network node K by.
In order to disclosure satisfy that when carrying out data transmission between the network node K and the network node K as destination node work as source node work of communication network for data transmission in end-to-end delay (delay) and/or the previously given requirement of delay variation (shake) aspect, in the active management according to the communication path set up in the communications network under the control of network management entity NM in the most packet-based communication network of Fig. 1.In principle, especially when due to the packet intermediate storage (so-called queuing) in network node K communication path along the determination between source node and destination node produce the packet of the forwarding time causing in each network node change congested time, end-to-end delay and jitter value may become critical.Its reason e.g. blocks output port or Priority Service in the packet of other intermediate storage with higher priority by sending other packet.The most deterministic owing to postponing, it is thus possible to produce variable delay and jitter value.
On the one hand the task of network management entity is to set up and manage the communication path formed in a communication network.On the other hand, the task of network management entity be at least within network nodes along the respective communication paths arrangement formed in the communications network port waiting queue in view of its waiting queue length monitor.Network management entity can determine the overload tolerance of port from this waiting queue length, wherein often can be inferred that the delay in data transmission and/or jitter problem from for one or more through overload tolerance involved, overload port communication path.There is multiple waiting queue (queue) in each port P typically for network node, these waiting queues are assigned to one or more priority (class of service).These priority are such as defined by IEEE 802.1P service type (Class of Service, CoS) or IP type of service (ToS).If involved overload tolerance exceedes previously given threshold value, namely the waiting queue length of the waiting queue of port is more than previously given threshold value, then set up the communication path of replacement under the port walking around overload via the port guided communication path of overload at least one.These paths are selected as at this so that critical port P or network node are not used.
This overload tolerance can be and the waiting directly proportional value of queue length.Equally, this overload tolerance can correspond to wait queue length, such as the byte quantity of the time till waiting queue processing is complete, etc..
Fig. 2 illustrates the communication network described in Fig. 1 in this example, sets up three communication path PF1, PF2, PF3 by network management entity NM in the communications network.This communication path 1 is stretched over network node 3 from network node 1 via network node 5 and 2.Communication path PF2 is stretched over network node 8 from network node 1 via network node 5 and 6.Communication path PF3 is stretched over network node 8 from network node 4 via network node 5 and 6.Thus in selected embodiment, all 3 communication paths PF1, PF2 and PF3 guide via network node 5, and wherein communication path PF2 and PF3 is also via common port P1(5) guide.Thus determining ground, packet may be occurred at port P1 (5) place congested, this packet congested all may causing for communication path PF2 and communication path PF3 postpones and/or shake.If that is formed by waiting queue length, exceed previously given threshold value in the overload tolerance of port P1 (5), then according to Fig. 3 by network node 5 to network management entity NM transmission message N.
Network management entity NM can infer, from in the overload tolerance of the communication path PF2, PF3 through port P1 (5), the delay and/or jitter problem being likely to occur.Due to this delay and/or jitter problem, network management entity NM is to two communication path PF2, and one of PF3 reconfigures.In the present embodiment, setting up the communication path PF2' replaced for communication path PF2, the communication path of this replacement is stretched over network node 8 from network node 1 via network node 2 and 3.
In order to set up communication path, network management entity NM uses known method for routing in principle.These communication paths such as can by directly in layer 3 routing table or layer 2 forward table typing set up.Set up or adaptation can also realize by measuring of affecting described routing table or forward table is carried out adaptation.This can be such as quickly generate tree (Rapid Spanning Tree, RSTP) or multiple spanning tree (Multiple Spanning Tree,
Ospf in the case of MSTP) (Open Shortest Path First,
OSPF) weighting or link cost and priority.Corresponding mechanism and action modes are that professional is by known in the art.
Transmit can carry out first along default path set in advance from the data of source node to destination node.This means first independently to form default path with communication path along its waiting queue length waiting queue stretched.When determining problem scenario in the case of monitoring network node K and waiting queue thereof continuously, network management entity NM is just intervened.
Request to setting up new communication path can be treated to so that new communication path avoids critical port or network node.This is the most exemplary illustrates, wherein illustrates from network node 1 via the new communication path PF4 of network node 4 and 7 to network node 6 via according to the communication path of Fig. 3.Although shortest path will extend to network node 6 from network node 1 via the port P1 (5) of network node 5, select the path via network node 4 and 7, with avoid on the port P1 (5) of network node 5 manifest congested.
In order to set up new communication path, determine that low first threshold and the highest Second Threshold are useful.When exceeding low first threshold, setting up new communication path, such as communication path PF4 via the network node replaced, it adds existing communication path PF1, PF2' and PF3 to.Also make existing communication path portion when exceeding higher Second Threshold change its course.
One or more threshold value can also be defined the most individually in principle so that message is transferred to network management entity NM by network node K when the corresponding limit is exceeded for each described network node.This makes to become unnecessary by this management entity constantly state of inquiring about and thus save the communication resource.
In order to determine overload tolerance, being preferably used and averagely wait queue length, wherein this averagely waiting queue length averagely calculates from detected the temporal of waiting queue length multiple on the previously given time period.Thus can avoid strong fluctuation.Alternatively, it is also possible to definition maximum waiting queue length, wherein this maximum wait queue length such as can be corresponding with higher Second Threshold above.Equally, use effective waiting queue length to determine that overload tolerance is also possible, wherein from the time in the past determine that this effectively waits queue length in current waiting queue length.Thus can consider to wait the historical record of queue length, the most such as, can carry out exponential smoothing.
In another configuration, can alternatively be limited to monitor waiting queue length, because it typically carries the data service sensitive to delay and jitter for the class of service (priority class such as determined) determined.
In addition to considering to be measured by overload above or below average, maximum or effective waiting queue length, it is also possible to derive delay or the absolute end-to-end value of shake by this overload tolerance by managing system entity.Multiple delay components are added: the overload calculated by the respective bandwidth of link is measured for this；Delay that produce within network nodes due to switching process, that can be estimated or measure；The propagation delay (propagation Delay(propagation delay) in all involved communication connections, (such as by the response mechanism being standardized in the scope of time synchronized according to IEEE 1588 or 802.1as) can be estimated or measure).This especially must be informed that to causing the application of data service or being favourable when communication path only just allows and is set up under the subsidiary conditions less than the delay determined or jitter value in current delay and/or jitter value.
Claims (8)
1. for the method improving the quality of the data transmission in packet-based communication network, this communication network includes multiple network node (K), the most each described network node (K) has a number of port (P), to these port assignment, at least one waits queue (Q) and the communication connection (KV) can set up to other network node (K) via these ports respectively, wherein
-at least waiting queue length along the waiting queue (Q) of the port (P) of the respective communication paths arrangement formed in the communications network in network node (K) is monitored by upper network management entity (NM)；
-from described waiting queue length, determine that the overload for involved one or more ports (P) is measured, wherein from the one or more communication path (PF1 for the port (P) through involved overload, PF2, PF3) overload tolerance in infer these data transmission in operation time delay and/or delay variation；
-when this overload tolerance exceedes previously given threshold value, it is at least one communication path (PF1 guided via the port (P) of overload by the upper network management entity (NM) of described network node (K), PF2, PF3) under the port (P) walking around this overload, set up the communication path (PF2') of replacement, with avoid on the port of described overload manifest congested
Wherein said communication path (PF1, PF2, PF3) is set up by described upper network management entity (NM),
The overload tolerance of the port (P) arranged in network node (K) is wherein at least considered along this new communication path (PF4) when setting up new communication path (PF4),
Wherein define the low first threshold of the overload tolerance of the port arranged along new communication path (PF4) within network nodes, in the case of exceeding this first threshold, set up the communication path (PF4) that this is new so that
-not considering with lower node (K) for this new communication path (KV): described node has the port of at least one overload, and the overload tolerance of the port of this overload exceedes this first threshold, or
-do not consider that its overload tolerance of node (K) exceedes the port of the overload of this first threshold, and
Wherein define the higher Second Threshold of the overload tolerance of the port that communication path (PF4) new along this within network nodes is arranged, determine in the case of exceeding this Second Threshold and set up for existing communication path (PF1, PF2, PF3) the communication path (PF2') of replacement.
Method the most according to claim 1, wherein sets up the communication path (PF2') of replacement under the network node (K) walking around the port (P) including at least one and transshipping.
Method the most according to claim 1, wherein in order to determine that one of following waiting queue length is processed by overload tolerance:
-averagely wait queue length, wherein this averagely waiting queue length is that multiple the temporal of waiting queue length detected on the previously given time period by waiting queue averagely calculate；And/or
The waiting queue length of-maximum；And/or
-by pass by time and current waiting queue length determine effectively wait queue length.
Method the most according to claim 1, wherein inquired about the waiting queue length of the port (P) of multiple network node (K) by upper network management entity (NM) with previously given interval, wherein this network management entity (NM) is that each described port (P) determines overload tolerance.
Method the most according to claim 1, wherein with time the most previously given upper interval and/or according to the previously given overall situation or the single threshold value of network node be exceeded, transmitted the waiting queue length of the port (P) of multiple network node (K) by network node (K) superior network management entity (NM), wherein this network management entity (NM) is that each described port (P) determines overload tolerance.
6., according to the method for one of the claims 1-5, wherein monitor overload tolerance according to the class of service of involved waiting queue (Q).
7., according to the method for one of the claims 1-5, from overload tolerance determined by the waiting queue (Q) arranged along the respective communication path (KV) formed in the communications network network node (K), wherein determine the operation time delay on involved communication path (KV) and/or postpone the end-to-end value of variation.
The most packet-based communication network, this communication network includes:
1) multiple network nodes (K),
Wherein this network node (K) includes a number of port (P), and to these port assignment, at least one waits queue (Q) and the communication connection (KV) can set up to other network node (K) via these ports respectively, and this network node includes:
-first device, in this network node (K) along the respective communication paths arrangement formed in the communications network port (P) waiting queue waiting queue length monitor；
-the second device, for determining overload tolerance from the waiting queue length for one or more involved ports (P)；And
-inquiring about or periodically providing the device of the waiting queue length of described port for the transmission of superior network management entity for upper network management entity；
And
2) for setting up the network management entity (NM) of the communication path (PF2') of communication path (PF1, PF2, PF3) and/or replacement in the communications network, wherein this network management entity includes:
-the three device, by the 3rd device from that obtained by corresponding network node (K), for the communication path (PF1 of one or more ports through involved overload (P), PF2, PF3) overload tolerance in infer data transmission in operation time delay and/or delay variation；
-the four device, when described overload tolerance exceedes previously given threshold value, communication path (the PF1 that can be guided via the port (P) of overload at least one by the 4th device, PF2, PF3) under the port (P) walking around this overload, set up the communication path (PF2') of replacement, with avoid on the port of described overload manifest congested
This network management entity wherein said be further configured so that:
The overload tolerance of the port (P) arranged in network node (K) is at least considered along this new communication path (PF4) when setting up new communication path (PF4),
The low first threshold of the overload tolerance of the port that definition is arranged along new communication path (PF4) within network nodes, sets up the communication path (PF4) that this is new in the case of exceeding this first threshold so that
-not considering with lower node (K) for this new communication path (KV): described node has the port of at least one overload, and the overload tolerance of the port of this overload exceedes this first threshold, or
-do not consider that its overload tolerance of node (K) exceedes the port of the overload of this first threshold, and
The higher Second Threshold of the overload tolerance of the port that definition is arranged along this new communication path (PF4) within network nodes, determine in the case of exceeding this Second Threshold and set up for existing communication path (PF1, PF2, PF3) the communication path (PF2') of replacement.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102011003321A DE102011003321A1 (en) | 2011-01-28 | 2011-01-28 | Method for increasing the quality of data transmission in a packet-based communication network |
| DE102011003321.1 | 2011-01-28 | ||
| PCT/EP2012/050873 WO2012101054A1 (en) | 2011-01-28 | 2012-01-20 | Method for improving the quality of data transmission in a packet-based communication network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103329490A CN103329490A (en) | 2013-09-25 |
| CN103329490B true CN103329490B (en) | 2016-08-10 |
Family
ID=45562983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201280006638.5A Active CN103329490B (en) | 2011-01-28 | 2012-01-20 | Improve method and the communication network of data transmission quality based on packet communication network |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US9191334B2 (en) |
| EP (1) | EP2638672A1 (en) |
| CN (1) | CN103329490B (en) |
| CA (1) | CA2825830C (en) |
| DE (1) | DE102011003321A1 (en) |
| WO (1) | WO2012101054A1 (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8819309B1 (en) | 2013-06-14 | 2014-08-26 | Arm Limited | Low latency bypass buffer |
| ES2622349T3 (en) * | 2013-07-01 | 2017-07-06 | Siemens Aktiengesellschaft | Control equipment, network node and procedure for exchanging data through a data network |
| EP3275141B1 (en) | 2015-03-25 | 2018-11-21 | British Telecommunications public limited company | Mobile telecommunications routing |
| CN106102126B (en) * | 2016-05-27 | 2019-09-06 | 新华三技术有限公司 | A kind of connection control method and device |
| US20170373982A1 (en) * | 2016-06-24 | 2017-12-28 | Huawei Technologies Co., Ltd. | System and method for mtu size reduction in a packet network |
| EP3777267A1 (en) | 2018-03-28 | 2021-02-17 | British Telecommunications public limited company | Roaming route optimization |
| CN108712346A (en) * | 2018-05-16 | 2018-10-26 | 天津芯海创科技有限公司 | A kind of load balancing is from routing data exchange structure and method |
| EP3751803A1 (en) * | 2019-06-13 | 2020-12-16 | Hughes Network Systems, LLC | Enhanced network communication using multiple network connections |
| DE102019218827B3 (en) * | 2019-12-04 | 2021-04-29 | Wago Verwaltungsgesellschaft Mbh | METHOD, DEVICE AND SYSTEM FOR OPTIMIZING DATA TRANSFER BETWEEN CONTROL DEVICES AND CLOUD SYSTEMS |
| CN112491732A (en) * | 2020-10-23 | 2021-03-12 | 苏州浪潮智能科技有限公司 | Storage network congestion management method, system, terminal and storage medium |
| US20220345409A1 (en) * | 2021-04-21 | 2022-10-27 | EMC IP Holding Company LLC | Controlling storage arraydata transmissions |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6222822B1 (en) * | 1996-04-23 | 2001-04-24 | Cisco Systems, Incorporated | Method for optimizing a digital transmission network operation through transient error monitoring and control and system for implementing said method |
| WO2004102898A1 (en) * | 2003-05-15 | 2004-11-25 | Siemens Aktiengesellschaft | Method and network node for self-regulating, autonomous, and decentralized traffic distribution in a multipath network |
| GB2404826A (en) * | 2003-08-01 | 2005-02-09 | Motorola Inc | Packet router which re-routes packet to an alternative output port when the primary output port buffer is overloaded |
| GB2467424A (en) * | 2009-01-28 | 2010-08-04 | Ibm | Managing overload in an Ethernet network by re-routing data flows |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002252640A (en) * | 2001-02-23 | 2002-09-06 | Fujitsu Ltd | Network repeater and method and system for the same |
| US6968374B2 (en) * | 2002-07-03 | 2005-11-22 | Telefonaktiebolaget Lm Ericsson (Publ) | Quality of service (QOS) mechanism in an internet protocol (IP) network |
| US20080008202A1 (en) * | 2002-10-31 | 2008-01-10 | Terrell William C | Router with routing processors and methods for virtualization |
| GB2395856A (en) * | 2002-11-26 | 2004-06-02 | King S College London | Method for reducing packet congestion at a network node |
| US20080205265A1 (en) * | 2007-02-22 | 2008-08-28 | Verizon Services Organization Inc. | Traffic routing |
-
2011
- 2011-01-28 DE DE102011003321A patent/DE102011003321A1/en not_active Withdrawn
-
2012
- 2012-01-20 WO PCT/EP2012/050873 patent/WO2012101054A1/en active Application Filing
- 2012-01-20 CA CA2825830A patent/CA2825830C/en active Active
- 2012-01-20 US US13/982,214 patent/US9191334B2/en active Active
- 2012-01-20 EP EP12702460.2A patent/EP2638672A1/en not_active Ceased
- 2012-01-20 CN CN201280006638.5A patent/CN103329490B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6222822B1 (en) * | 1996-04-23 | 2001-04-24 | Cisco Systems, Incorporated | Method for optimizing a digital transmission network operation through transient error monitoring and control and system for implementing said method |
| WO2004102898A1 (en) * | 2003-05-15 | 2004-11-25 | Siemens Aktiengesellschaft | Method and network node for self-regulating, autonomous, and decentralized traffic distribution in a multipath network |
| GB2404826A (en) * | 2003-08-01 | 2005-02-09 | Motorola Inc | Packet router which re-routes packet to an alternative output port when the primary output port buffer is overloaded |
| GB2467424A (en) * | 2009-01-28 | 2010-08-04 | Ibm | Managing overload in an Ethernet network by re-routing data flows |
Also Published As
| Publication number | Publication date |
|---|---|
| US20130315062A1 (en) | 2013-11-28 |
| WO2012101054A1 (en) | 2012-08-02 |
| CA2825830C (en) | 2018-06-26 |
| US9191334B2 (en) | 2015-11-17 |
| CA2825830A1 (en) | 2012-08-02 |
| DE102011003321A1 (en) | 2012-08-02 |
| CN103329490A (en) | 2013-09-25 |
| EP2638672A1 (en) | 2013-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103329490B (en) | Improve method and the communication network of data transmission quality based on packet communication network | |
| US8115617B2 (en) | Alarm reordering to handle alarm storms in large networks | |
| KR102104047B1 (en) | Congestion control in packet data networking | |
| US20060250964A1 (en) | Traffic flow determination in communications networks | |
| US8493869B2 (en) | Distributed constraints-based inter-domain network traffic management | |
| EP2658192A1 (en) | Path weighted equal-cost multipath | |
| EP2263354B1 (en) | Admission control in a packet network | |
| WO2001095641A2 (en) | Multi-path dynamic routing algorithm | |
| EP1776813A2 (en) | Method for forwarding traffic having a predetermined category of transmission service in a connectionless communications network | |
| KR20160041631A (en) | Apparatus and method for quality of service aware routing control | |
| CN | A proactive flow admission and re-routing scheme for load balancing and mitigation of congestion propagation in SDN data plane | |
| Chiang et al. | A multipath transmission scheme for the improvement of throughput over SDN | |
| US20230017561A1 (en) | Network Device, System and Method For Cycle-Based Load Balancing | |
| TWI556599B (en) | Network controlling method and network controller | |
| Leonardi et al. | Joint optimal scheduling and routing for maximum network throughput | |
| Chamania et al. | A comparative analysis of the effects of dynamic optical circuit provisioning on IP routing | |
| Tang et al. | Parallel LSPs for constraint-based routing and load balancing in MPLS networks | |
| Farrel | RFC 9522: Overview and Principles of Internet Traffic Engineering | |
| Nakayama | Rate-based path selection for shortest path bridging in access networks | |
| Wen et al. | Understanding multi-path routing algorithms in datacenter networks | |
| Naumov | Aggregate multipath QoS routing in the Internet | |
| Varela et al. | Multi-Service: A Service Aware Routing Protocol for the Next Generation Internet. | |
| Varela et al. | Multi-service routing: A routing proposal for the next generation Internet | |
| El Kamel et al. | An adaptive switching te based on notification subscription within mpls domains | |
| Singh et al. | Application of N jobs M machine Job Sequencing Technique for MPLS Traffic Engineering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |